Enhance progress information

clustering.R

@@ -1,4 +1,5 @@
 library(data.table)
+library(progress)
 library(rlog)
 
 #' Process genes clustering their distance to telomeres.
@@ -17,15 +18,22 @@ process_clustering <- function(distances, species_ids, gene_ids) {
     results <- data.table(gene = gene_ids)
     gene_count <- length(gene_ids)
 
-    for (i in 1:gene_count) {
-        gene_id <- gene_ids[i]
-
     log_info(sprintf(
-            "[%3i%%] Processing gene \"%s\"",
+        "Clustering %i genes from %i species",
-            round(i / gene_count * 100),
+        gene_count,
-            gene_id
+        length(species_ids)
     ))
 
+    progress <- progress_bar$new(
+        total = gene_count,
+        format = "Clustering genes [:bar] :percent (ETA :eta)"
+    )
+
+    for (i in 1:gene_count) {
+        progress$tick()
+
+        gene_id <- gene_ids[i]
+
         data <- distances[
             species %chin% species_ids & gene == gene_id,
             .(species, distance)

correlation.R

@@ -1,4 +1,5 @@
 library(data.table)
+library(progress)
 library(rlog)
 
 #' Compute the mean correlation coefficient comparing gene distances with a set
@@ -15,24 +16,29 @@ library(rlog)
 #' @param reference_gene_ids Genes to compare to.
 process_correlation <- function(distances, species_ids, gene_ids,
                                 reference_gene_ids) {
-    log_info("Processing genes for correlation")
-
     results <- data.table(gene = gene_ids)
     gene_count <- length(gene_ids)
     reference_count <- length(reference_gene_ids)
 
+    log_info(sprintf(
+        "Correlating %i genes from %i species with %i reference genes",
+        gene_count,
+        length(species_ids),
+        reference_count
+    ))
+
+    progress <- progress_bar$new(
+        total = gene_count,
+        format = "Correlating genes [:bar] :percent (ETA :eta)"
+    )
+
     # Prefilter distances by species.
     distances <- distances[species %chin% species_ids]
 
     for (i in 1:gene_count) {
+        progress$tick()
+
         gene_id <- gene_ids[i]
-
-        log_info(sprintf(
-            "[%3i%%] Processing gene \"%s\"",
-            round(i / gene_count * 100),
-            gene_id
-        ))
-
         gene_distances <- distances[gene == gene_id]
 
         if (nrow(gene_distances) < 12) {

input.R

@@ -1,5 +1,6 @@
 library(biomaRt)
 library(data.table)
+library(progress)
 library(rlog)
 library(stringr)
 
@@ -115,6 +116,23 @@ retrieve_genes <- function() {
 #'  - `gene` Ensembl gene ID.
 #'  - `distance` Distance to nearest telomere in base pairs.
 retrieve_distances <- function(species_ids, gene_ids) {
+    # Exclude the human from the species, in case it is present there.
+    species_ids <- species_ids[species_ids != "hsapiens"]
+
+    species_count <- length(species_ids)
+    gene_count <- length(gene_ids)
+
+    log_info(sprintf(
+        "Retrieving distance data for %i genes from %i species",
+        gene_count,
+        species_count
+    ))
+
+    progress <- progress_bar$new(
+        total = gene_count,
+        format = "Retrieving distance data [:bar] :percent (ETA :eta)"
+    )
+
     # Special case the human species and retrieve all available distance
     # information.
 
@@ -148,19 +166,10 @@ retrieve_distances <- function(species_ids, gene_ids) {
         )
     ]
 
-    # Exclude the human from the species, in case it is present there.
-    species_ids <- species_ids[species_ids != "hsapiens"]
-
-    species_count <- length(species_ids)
-
     for (i in 1:species_count) {
         species_id <- species_ids[i]
 
-        log_info(sprintf(
+        progress$tick()
-            "[%3i%%] Loading species \"%s\"",
-            round(i / species_count * 100),
-            species_id
-        ))
 
         ensembl <- useDataset(
             sprintf("%s_gene_ensembl", species_id),